How to speed up caffe classifer in python

问题

I am using python to use caffe classifier. I got image from my camera and peform predict image from training set. It work well but the problem is speed very slow. I thinks just 4 frames/second. Could you suggest to me some way to improve computational time in my code? The problem can be explained as following. I have to reload an network model age_net.caffemodel that its size about 80MB by following code

age_net_pretrained='./age_net.caffemodel'
age_net_model_file='./deploy_age.prototxt'
age_net = caffe.Classifier(age_net_model_file, age_net_pretrained,
           mean=mean,
           channel_swap=(2,1,0),
           raw_scale=255,
           image_dims=(256, 256))

And for each input image (caffe_input), I call the predict function

prediction = age_net.predict([caffe_input])

I think that due to size of network is very large. Then predict function takes long time to predict image. I think the slow time is from it.
This is my full reference code. It changed by me.

from conv_net import *

import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
import os
caffe_root = './caffe' 
import sys
sys.path.insert(0, caffe_root + 'python')
import caffe
DATA_PATH = './face/'
cnn_params = './params/gender_5x5_5_5x5_10.param'
face_params = './params/haarcascade_frontalface_alt.xml'
def format_frame(frame):
    img = frame.astype(np.float32)/255.
    img = img[...,::-1]
    return img   

if __name__ == '__main__':    
    files = glob.glob(os.path.join(DATA_PATH, '*.*'))

    # This is the configuration of the full convolutional part of the CNN
    # `d` is a list of dicts, where each dict represents a convolution-maxpooling
    # layer. 
    # Eg c1 - first layer, convolution window size
    # p1 - first layer pooling window size
    # f_in1 - first layer no. of input feature arrays
    # f_out1 - first layer no. of output feature arrays
    d = [{'c1':(5,5),
          'p1':(2,2),
          'f_in1':1, 'f_out1':5},
         {'c2':(5,5),
          'p2':(2,2),
          'f_in2':5, 'f_out2':10}]

    # This is the configuration of the mlp part of the CNN
    # first tuple has the fan_in and fan_out of the input layer
    # of the mlp and so on.
    nnet =  [(800,256),(256,2)]    
    c = ConvNet(d,nnet, (45,45))
    c.load_params(cnn_params)        
    face_cascade = cv2.CascadeClassifier(face_params)
    cap = cv2.VideoCapture(0)
    cv2.namedWindow("Image", cv2.WINDOW_NORMAL)

    plt.rcParams['figure.figsize'] = (10, 10)
    plt.rcParams['image.interpolation'] = 'nearest'
    plt.rcParams['image.cmap'] = 'gray'
    mean_filename='./mean.binaryproto'
    proto_data = open(mean_filename, "rb").read()
    a = caffe.io.caffe_pb2.BlobProto.FromString(proto_data)
    mean  = caffe.io.blobproto_to_array(a)[0]
    age_net_pretrained='./age_net.caffemodel'
    age_net_model_file='./deploy_age.prototxt'
    age_net = caffe.Classifier(age_net_model_file, age_net_pretrained,
               mean=mean,
               channel_swap=(2,1,0),
               raw_scale=255,
               image_dims=(256, 256))
    age_list=['(0, 2)','(4, 6)','(8, 12)','(15, 20)','(25, 32)','(38, 43)','(48, 53)','(60, 100)']
    while(True):

        val, image = cap.read()        
        if image is None:
            break
        image = cv2.resize(image, (320,240))
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        faces = face_cascade.detectMultiScale(gray, 1.3, 5, minSize=(30,30))

        for f in faces:
            x,y,w,h = f
            cv2.rectangle(image, (x,y), (x+w,y+h), (0,255,255))            
            face_image_rgb = image[y:y+h, x:x+w]
            caffe_input = cv2.resize(face_image_rgb, (256, 256)).astype(np.float32)
            prediction = age_net.predict([caffe_input]) 
            print 'predicted age:', age_list[prediction[0].argmax()]       
        cv2.imshow('Image', image)
        ch = 0xFF & cv2.waitKey(1)
        if ch == 27:
            break
        #break

回答1:

Try calling age_net.predict([caffe_input]) with oversmaple=False:

prediction = age_net.predict([caffe_input], oversample=False)

The default behavior of predict is to create 10, slightly different, crops of the input image and feed them to the network to classify, by disabling this option you should get a x10 speedup.

回答2:

You can also try channel pruning your network. It's an algorithm that effectively prune channels in each layer, which could speed up network 2-5x. The github address is : https://github.com/yihui-he/channel-pruning

来源：https://stackoverflow.com/questions/30822009/how-to-speed-up-caffe-classifer-in-python